161 results about "Decision strategy" patented technology

The invention discloses a man-machine interaction method and system based on artificial intelligence. The method includes the following steps of receiving input information input by a user through an application terminal, obtaining the intent information of the user according to the input information of the user, distributing the input information to at least one interaction service subsystem according to the intent information, receiving the return result returned by the interaction service subsystems, generating a user return result according to the return result through a preset decision strategy, and providing the user return result to the user. By means of the method and system, the man-machine interaction system is virtualized instead of being instrumentalized, and the user can obtain the relaxed and pleasure interaction experience in the intelligent interaction process through chat, research and other service. The search in the form of keywords is improved into the search based on natural languages, the user can express demands through flexible and free natural languages, and the multi-round interaction process is closer to the interaction experience among humans.

A real time decisioning service comprising a set of powerful tools accessible in ASP mode allowing an end user to create, configure, test, and deploy decision engines to automate real time decisions, comprising both expert and custom analytic models used within decision strategies, and comprising systems integration and strategy consulting is provided. An exemplary decision system is described.

The present invention relates to a system and methodology to enable a plurality of information associated with electronic messages to be automatically prioritized by a message urgency system for transmittal to a user or system. The message urgency system can employ classifiers that can be explicitly and / or implicitly trained to prioritize or triage one or more received messages according to a learned importance to the user. An adaptable and configurable graphical user interface is provided in order to manage the prioritized information. The interface facilitates system personalization according to user desires of how messages are received and subsequently processed by the user. Display and input adjustments are provided in a plurality of selectable pages to enable the personalization of the system. Display options include status and summary views of various configuration and adjustment options that alter the characteristics of how messages are presented to the user. Configuration and adjustment options include profile options, routing options, alerting options, chunking options, schedule options, and other context-sensitive control options, one or more rules that act in conjunction with a routing system, learning status and configuration options for guiding and inspecting the state of learning of the message urgency system along with device option configurations for controlling messages output to a selected message reception and display device.

The invention discloses a robot visual processing method based on an attention mechanism. The method includes the following steps that image preprocessing is conducted, wherein basic processing is conducted on an image and comprises color spatial switching, edge extracting, image conversion and image thresholding; feature extracting is conducted, wherein five kinds of feature information of the skin color, the color, the texture, the movement and the space coordinates of the preprocessed image are extracted; arbitration decision is conducted, wherein the extracted information is selectively distributed to an upper-layer function application subsystem needing the feature information according to a certain arbitration decision strategy; function application is conducted, wherein corresponding operation is conducted on the feature information which is submitted after arbitration decision to achieve function application, in other words, a direct implementation layer of visual application of a robot comprises five parts of human face detecting, color recognizing, movement detecting and tracking, gesture interaction and the attention mechanism. The robot visual processing method can provide more complete visual information of the human face, the skin color, the gesture and the like for the robot, and the movement detection capability and the tracking and planning capability are achieved.

In a method for dynamically optimizing resource utilization in a system over time according to one or more objectives, data including information indicative of current environmental conditions, upcoming environmental conditions, a current state of a system configuration, and current system operating conditions is dynamically updated. Automatic analysis of the data using a probabilistic model based on conditional relationships is performed periodically. For each periodically generated set of possible system control actions, a probabilistic model is used to automatically analyze each possible system control action and an optimal system control action is selected based on a set of current utility functions. For each periodically generated set of possible system control actions, control of the system according to the optimal system control action selected from the possible system control actions. Resource optimization couples condition-based and environmental monitoring with automated reasoning and decision making technologies, to develop real time optimal control and decision strategies.

The invention discloses a greenhouse multi-model information fusion based technology for regulating and controlling the greenhouse environment. According to environmental information such as the temperature, the humidity, the illumination intensity and the carbon dioxide concentration inside a greenhouse, which is obtained by a greenhouse environment information collecting sensor, three kinds of greenhouse environment control models which are based on a set value, the illumination and the accumulated temperature are used respectively for extracting feature vectors, multi-information fusion of feature vectors of three kinds of regulating and controlling methods is conducted by using a Dempster / Shafer (D-S) evidence theory method, an environment optimization controlling and regulating decision strategy is established, and coordination of short-scale and long-scale control requirements of the greenhouse is achieved. An actuating mechanism is controlled by a greenhouse environment controller to act to achieve real-time control of greenhouse environmental parameters.

The invention discloses a lane changing decision-making method and system for an autonomous vehicle based on a rolling game. The method is characterized in that rolling optimization is carried out onthe optimum decision within each time domain, a long-run profit function is considered within each time domain, the different profit functions are set through driving radicalness degrees, surroundingvehicles and the intelligent vehicle are simultaneously considered within each time domain, and the optimum decision-making strategy for the intelligent vehicle is obtained through bi-level programming; and information of the state of the intelligent vehicle, the states of the surrounding vehicles and the road state is updated at a next moment, and a whole game process is then repeated until a stop state is achieved. The method and system disclosed by the invention has the advantages that the conformity between decisions of the autonomous vehicle and humans can be improved; and a rolling optimization strategy is introduced, so that uncertainties in the vehicle and an environment can be efficiently handled.

An embodiment of the invention provides a policy control method, a policy control device and a policy control system for data services. The method includes: acquiring first policy information from a policy and charging rule function network element, wherein the first policy information is decision policy information needing to be judged and enforced by a policy and charging enforcement function network element based on the services; when a service request is received from a user, acquiring service information needed in match with the first policy information from the service request; and when the service information satisfies the first policy information, performing policy control for the service information according to the first policy information. The method, the device and the system in the embodiment solve the technical problem of more interactive times between the PCRF (policy and charging rule function) network element and the PCEF (policy and charging enforcement function) network element in policy control of frequently modified service request information or result associated policy control in the prior art.

The invention relates to the technical field of energy internet planning, in particular to a game theory-based regional energy internet planning mathematical model and planning method, which comprisesthe following steps of: establishing a model of a distributed power supply, an energy storage system and a combined cooling heating and power system which are suitable for game theory planning and analysis; using A public energy operator, a service provider of distributed energy and a user as game participants, planning construction capacity, using pricing strategies and energy using behaviors asrespective decision variables, using the full life cycle income of equipment as earnings, and establishing different game models for regional energy internet planning; Establishing a specific game model under multiple modes according to the decision strategy of each participant; And carrying out solving through an iterative optimization algorithm, comparing and analyzing Nash equilibrium solutions under various game modes, and finally selecting the Nash equilibrium solution under the benefit maximization of all parties as a planning scheme of the regional energy internet.

The invention relates to a decision planning method for automatic driving of a special vehicle. The method comprises the steps of: 1) an automatic driving operation module obtaining the current position and pose of a vehicle; 2) projecting environment information sent by a perception system to a grid map, and generating an environment map; 3) the automatic driving operation module obtaining a control instruction of a current work executor and issuing the control instruction; 4) the automatic driving operation module obtaining a task reference route, performing trajectory cluster planning combined with vehicle dynamics constraints by a route-speed decomposed trajectory planning method, obtaining a basic trajectory cluster executable by the vehicle, and fusing the basic trajectory cluster and the task reference route to obtain an executable trajectory cluster; and 5) performing safety and high efficiency selection on the planned executable trajectory cluster, and finally generating a high-gain trajectory. According to the decision planning method for the automatic driving of the special vehicle, compared with the prior art, the method has the advantages of improving obstacle avoidance success rate, automatic decision, multi-mode trajectory decision strategy, achieving automatic driving safety and the like.

The invention discloses an energy-saving optimization method for cooperative control on multiple trains. The method comprises the steps of adopting a stop position of each station on a train running route as a decision position of a train, and adopting the train passing by the decision position at the current moment as a decision train; acquiring the information of other trains in the same power supply interval at the current moment by the decision train; setting a decision strategy of all trains at a next moment in the same power supply interval; calculating renewable kinetic energy of all the trains in the same power supply interval; determining the decision strategy of the decision train at the next moment according to the renewable kinetic energy. By adopting the method, the utilization of renewable brake energy is realized, and the total energy consumption of all the trains on the route can be reduced.

A method of lane change and path planning that receives sensed signals from multiple sensors through a car computer on a vehicle to generate multiple traveling speed time-sorted information and multiple surrounding circumstance time-sorted information, and to further generate a 3×3 grid corresponding to the surroundings of the vehicle; when receiving a signal to switch on the turn signals, the car computer selects data within a time interval from those traveling speed time-sorted information and surrounding circumstance time-sorted information, respectively; and then the selected data is to be processed together with the 3×3 grid to generate a lane change space, and through a decision strategy to determine whether the lane change space complies with a safety movement strategy, and then the car computer generates a planned path of movement, such that a safest space for assisting lane change is provided for improving convenience and safety.

The application discloses a DGA domain name detection model construction method and device, a server and a storage medium. The method includes the following steps of: acquiring a training data set, wherein the training data set includes DGA domain names and legal domain names; dividing the training data set into a plurality of training data sub-sets, wherein each training data sub-set includes atleast one DGA domain name and at least one legal domain name; training each training data sub-set by using a classification algorithm to obtain a plurality of detection sub-models; sequentially inputting test samples into each detection sub-model to obtain a prediction label set of the test samples; and fusing the prediction label set according to a decision strategy to obtain a final label of thetest samples. According to the DGA domain name detection model construction method provided by the embodiment of the application, the plurality of detection sub-models are obtained by grouping the training data set, the complete learning of the training data set can be realized, and the characteristics of actual DGA domain names can be embodied.

The invention discloses a program execution method, which is applied to the decentration system based on a blockchain. A target program in the decentration system is recorded to the distributed database of the blockchain, and the execution process of the target program is jointly decided by each user in a preset user group. The method comprises the following steps that: collecting a decision result independently submitted by each user in the preset user group on the basis of a held private key; on the basis of the collected decision result and a preset decision strategy, determining whether the target program passes the decision or not; and if the target program passes the decision, publishing the execution result of the target program to the blockchain. By use of the method, the execution stability of the target program in the decentration system can be improved.

The invention provides a transformer anti-aging repair strategy making method based on a semi-Markov chain. The method comprises the following steps of (1) building an aging model for preventive repair of a transformer; (2) obtaining an index of the aging state of the transformer, wherein the index parameter Z is {1, 2, 3, to L}; and (3) building the confidence level of the aging state of the transformer; and (4) according to the confidence level of the aging state of the transformer, performing repeated iteration to obtain the optimum repair strategy and the total cost of the repair strategy. The existing transformer preventive repair decision strategy can be optimized; the economic loss due to equipment use stop during the equipment overhaul is considered; an aging model of the transformer based on random failure is built; the semi-Markov decision is used for evaluating the transformer state; meanwhile, the confidence level of an observation index is built; and the state evaluation result of the transformer equipment is corrected through a Bayesian theory. The model and evaluation decision method built by the invention have the advantages that the transformer preventive repair decision strategy can be optimized; the use efficiency of the transformer is improved; and meanwhile, the repair cost is reduced.

The invention relates to a resource allocation and unloading decision-making method based on multi-agent architecture reinforcement learning, and belongs to the technical field of mobile communication. According to the method, excitation constraints, energy constraints and network resource constraints are considered, wireless resource allocation, computing resource allocation and unloading decisions are jointly optimized, and a random optimization model for maximizing the QoE of a total user of a system is established and converted into an MDP problem. Secondly, according to the method, an original MDP problem is subjected to factorization, and a Markov game model is established; then, the method provides a centralized training and distributed execution mechanism based on an actor-evaluator algorithm. In the centralized training process, multiple agents obtain global information through cooperation, resource allocation and task unloading decision strategy optimization are achieved, andafter the training process is finished, all the agents independently conduct resource allocation and task unloading according to the current system state and strategy. According to the invention, theQoE of the user can be effectively improved, and the time delay and the energy consumption are reduced.

The invention provides a credibility based cooperative spectrum sensing method, comprising the steps of initialization, local sensing of the unauthorized user, local decision, sensing information quantization, credibility fusion, decision fusion and the like. The invention gives the credibility of local sensing of the unauthorized user under the condition of unknown prior information, reduces thenetwork overhead of cooperative sensing by adopting the mixed threshold decision strategy uniting the base station and the unauthorized user and quantizing the local sensing result and has good sensing property.

The invention relates to a W1MAX network switching method based on system capacity, belonging to the technical field of wireless network. The W1MAX network switching method comprises the following steps: currently maximum effective capacity of a base station is calculated; the base station informs a mobile terminal currently idle capacity of all neighbors by broadcast messages of the neighbors; the neighbor broadcast messages are used as carriers to update effective idle capacity of the current base station and the adjacent base stations dynamically to the mobile terminal; when the capacity of the current base station and the adjacent base stations meets the conditions of switching and triggering, the mobile terminal starts switching and scanning of the cell; the mobile terminal selects a target cell and carries out cell switching according to the cell decision strategy. Compared with the prior art, the W1MAX network switching method can improve the switching performance of the mobile terminal in the W1MAX network, thus improving the throughput of the whole network and reducing packet loss.

The invention discloses a method for detecting and disposing marine organisms invading nuclear power plant cold source sea areas. The method comprises the following steps of: detecting a marine organism condition of a nuclear power plant cold source sea area by utilizing a sonar detector and an underwater camera, respectively calculating a first marine organism density and a second marine organismdensity according to the detection condition, and fusing the first and second marine organism densities to form a comprehensive density of invading marine organisms, wherein the calculation correctness is above 95%; obtaining invading strength indexes of the marine organisms in the nuclear power plant cold source sea area through a fuzzy neural network algorithm by considering marine environmentfactors; and finally forming a decision strategy table according to the invading strength so as to provide an effective disposing method for workers. According to the method for detecting and disposing marine organisms invading nuclear power plant cold source sea areas, the pre-warning operation time is within 30 seconds; and according to simulation experiment data, the false alarm rate of the pre-warning is not greater than 5%, so that urgent operation stop events, caused by invasion of marine organisms, of reactors are effectively avoided.

Systems described herein provide structures and functionality for transforming passive analytics systems into systems that can actively modify software behavior based on analytic data to improve software performance relative to configurable goal metrics. An example method generally includes receiving, from a policy generator, a decision-making policy specifying actions for a software application to perform upon detection of decision-point events; receiving a decision-making request from the software application; retrieving, from a data repository, time-series data in a session associated with the consumer identifier; selecting one or more of the different actions for the software application to perform by comparing the time-series data and the event type to the decision-making policy; sending an indication of the selected actions in response to the decision-making request; and updating the time-series data in the session associated with the consumer identifier to reflect the decision-point event and the one or more selected actions.

Content-centric networking is one solution of an information-centric networking thought. The invention discloses a centralized caching decision strategy in the content-centric networking. Under the architecture of the content-centric networking, researches of basic functions, such as data naming, content forwarding and intranet caching of information-centric networking, are realized by utilizing the existing framework adopting a SDN; the centralized caching decision strategy is provided; a centralized controller is placed in the content-centric networking; the controller generates one caching list for each node by collecting all node request information, and deterministically guides each node to cache contents; therefore, the transmission flow in the network is minimized; and the user request delay is reduced.

The invention provides an automatic hologram reestablishing method. According to the method, at first, a focus evaluation function is designed and can reflect image detail information and the anti-noise property advantage of a variance by utilizing local variance distribution, and the standard deviation of the local variance distribution serves as an index judging the image clarity degree, so that realization of automatic reestablishment becomes possible; secondly, a decision strategy is designed and used for deciding which performance of a focus function value serves as reaction of the target reestablishment distance, and a maximum value of the function value is adopted as a reaction value of the target reestablishment distance; finally, the separation distance is discussed, the separation distance is the step side in search and directly influences the real-time property of automatic reestablishment, a strategy of gradually refining the separation distance from big to small and carrying out feedback in time is adopted for carrying out research, and therefore the operation efficiency is improved. The method can achieve high-accuracy automatic reestablishment and has certain real-time property and universality.

The embodiment of the invention provides a dialogue method and device and equipment. The dialogue method comprises the following steps: acquiring utterance information input by a user; In a dialogue model, determining a dialogue skill model corresponding to the utterance information, the dialogue model comprising an intention recognition model and a plurality of dialogue skill models; Completing aconversation with the user according to the determined conversation skill model. The dialogue model is obtained by performing reinforcement learning according to the first return information of eachdialogue skill model and the second return information of the intention recognition model. each dialogue skill model and the intention identification model influence each other; When the intention recognition model carries out intention recognition on the utterance information, the intention recognition model not only depends on a decision strategy of the intention recognition model, but also is influenced by each conversation skill model, so that the intention recognition accuracy can be improved, and the conversation process accuracy and fluency are improved.

The invention relates to the field of automatic control of aircraft, and provides a track simulation system method based on a large-pack line game strategy, aiming at solving the problem that the maneuvering decision-making strategy and the trajectory of a flight device are rapidly estimated. The system comprises the following steps: the situational awareness and decision module is configured to acquire the attitude data of the flight device and select different tactical tasks according to the gesture data; the abnormal management module is configured to perform flight task switching on the flight device according to the flight device attitude data and the preset multiple maneuver missions; the real-time maneuvering flight module is configured to calculate the control of each flight sub-operation of the flight device in flight based on the attitude data and the flight path, forming a target attitude and a target track and a target trajectory solution calculation module to solve the target attitude and the target trajectory by utilizing the multi-degree-of-freedom equation to realize the output of the target track of the flight device. Carrying out rapid prediction on the maneuvering decision strategy and the trajectory of the flight device.

The invention discloses a dynamic and intelligent subject and resource classification method and a fine-grain authority management method based on the classification method. The subject classification method is a dynamic and intelligent classification method and realized by various algorithms carried out to subjects, subject properties, context and data sources. As to a given subject, only an algorithm rule is required for determining whether the subject belongs to a class. The resource classification method is quite similar to the subject classification method and can carry out the algorithm to resources and resource properties. Both a fine-grain authorization decision-making method and a fine-grain authorization inquiry method are applied to the filed of authority management. The fine-grain authorization decision-making method defines authority decision strategies based on subject classification and resources classification. When a certain subject requests operation to a certain resource, the strategies are assessed to permit or deny the request. If the request is denied, refusal reasons are returned. The fine-grain authority inquiry method defines authority inquiry strategies based on the subject classification and a data inquiry template. When a certain subject requests certain inquiry, the strategies are assessed and inquiry results are returned. The authority strategies based on classification are characterized by simpleness, strong reusability, easy implementation and the like.

The present invention relates to a heterogeneous wireless network joint admission control method. The method comprises the steps of defining a system state space, determining network overall energy consumption, setting an action set, determining a gain model, calculating a state transition probability and a maximized long-term expected gain, and using an improved value iteration algorithm to obtain an optimal strategy. According to the method, optimal admission control is used, in the condition that a network state and a service blocking rate / dropping rate are changed, based on the above resources, the allowance or rejection of calling access or switching is adaptively determined and controlled, and minimal energy consumption is obtained. By using a network overall energy consumption model, while the switching dropping rate and calling blocking rate are reduced, the QoS of a whole system is effectively ensured, the resource is effectively utilized, and two sides are balanced. Based on a semi-Markov decision process, a whole network admission decision strategy is obtained, and the computation and complexity of an algorithm are reduced.

The invention discloses a clean energy power grid 'source load domain' coordination regulating method, and belongs to the field of electric system operation and control. The clean energy power grid 'source load domain' coordination regulating method fully considers power grid balance adjustment demands, multi-source margin adjustment characteristics, interactive load regulation characteristics, multi-source regulation cost characteristics, clean energy consumption maximization and other factors, defines a multi-control domain scheduling mode, introduces a decision coefficient vector of a normal control domain, exception control domain and emergency control domain, through the control priority of each domain, a source load domain coordination regulating optimization model is established, and satisfies system abundant demands with the minimum regulating quantity to achieve maximum clean energy consumption. According to the clean energy power grid 'source load domain' coordination regulating method, a running new method of multi-domain control is introduced, the multi-source and multi-load regulating characteristics are completely involved, a multi-source and multi-load decision strategy is fully optimized, system adjustment margin, clean energy consumption and regulation cost amount and other factors are integrated to achieve the overall optimization of system resource regulating.